Anthropic · Frontier
Claude Opus 5
Claude Opus 5 is Anthropic's flagship model for advanced coding, long-running agentic tasks, research, and complex knowledge work.
- Reasoning
- Tools
- Vision
- Structured output
- PDF input
- Input
- Text, Images
- Output
- Text
- Reasoning effort
- low · medium · high · xhigh · max
- Discovery tier
- Frontier
Pricing
USD per 1M tokens- Input
- $5.00
- Output
- $25.00
- Cache read
- $0.50
- Cache write
- $6.25
- $10.00 for a 1-hour cache
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 128K
- Average output (7 days)
- 1.5K tokens
- Longer than 86% of 473 models
Side by side
Compare models
Put Claude Opus 5 next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
48.1
Tested at high reasoning effort
Better than 95% of 326 scored models
Indexes
Coding Index
76.5Composite of the coding evaluations
Better than 92% of 168 scored models
Agentic work
AutomationBench-AA
53.6%Workflow automation, penalized for guardrail violations
Better than 67% of 173 scored models
AutomationBench-AA tasks completed
25.3%Workflows finished end to end without a guardrail violation
Better than 73% of 173 scored models
AA-Briefcasev1.1
1,558 EloAgentic knowledge work, rated head to head
Better than 89% of 166 scored models
GDPval-AAv2.1
1,595 EloEconomically valuable occupational tasks, rated head to head
Better than 83% of 187 scored models
Document reasoning
GDP.pdf
19.6%Professional reasoning over PDF documents, all-pass rate
Better than 75% of 171 scored models
AA-LCRv1.1
79.0%Reasoning across long documents
Better than 72% of 309 scored models
MLCR-AA
11.7%Long-context reasoning over medical records
Better than 44% of 121 scored models
Reasoning and knowledge
Humanity’s Last Exam
52.8%Expert-level questions across academic fields
Better than 98% of 323 scored models
GPQA Diamond
93.7%Graduate-level science questions
Better than 94% of 291 scored models
Coding
Terminal-Benchv4.0
46.0%Practical software engineering in a terminal
Better than 91% of 171 scored models
SciCode
55.4%Scientific computing in Python
Better than 78% of 174 scored models
Legacy evaluations
AA-LCR (unversioned)
79.0%Long-context reasoning, earlier grading
Better than 72% of 309 scored models
Scores from Artificial Analysis, updated Oct 26, 2026. Claude Opus 5 was tested at high reasoning effort; compare scores measured at the same effort.Artificial Analysis
- #10Combined16.9%
Ranks among Noumen catalog models on Combined leaderboards. Only top-20 placements are listed.
- #1Roleplay96.9%
- #3Creative writing62.2%
- #6Coding30.3%
- #5Math34.4%
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- #11Overall1490.9
- #14Coding1533.9
- #5Math1520.5
- #9Longer Query1502.7
- #11Creative Writing1473.8
- #8Instruction Following1495.4
- #11Hard Prompts1515.5
- #7Chinese1546.2
- #12English1493.9
- #11Exclude Ties1505.6
- #4Expert1537.6
- #17French1505.7
- #2German1512.3
- #12Hard Prompts English1513.5
- #15Industry Business And Management And Financial Operations1485.4
- #13Industry Entertainment And Sports And Media1463.0
- #8Industry Legal And Government1503.9
- #10Industry Life And Physical And Social Science1514.0
- #4Industry Mathematical1531.6
- #8Industry Medicine And Healthcare1512.5
- #13Industry Software And It Services1523.4
- #12Industry Writing And Literature And Language1481.4
- #6Japanese1509.3
- #2Korean1496.4
- #13Non English1481.3
- #6Polish1503.6
- #13Russian1497.1
- #8Spanish1489.8
- #10Vision Style Control Overall1287.9
- #3Vision Style Control · Chinese1363.2
- #17Vision Style Control · Creative Writing Vision1275.3
- #6Vision Style Control · Diagram1328.6
- #11Vision Style Control · English1281.0
- #14Vision Style Control · Homework1323.3
- #9Vision Style Control · Ocr1304.1
- #7WebDev Overall1690.7
- #6WebDev · Image To Webdev1661.8
- #7WebDev · Webdev1690.7
- #9WebDev · Webdev-html1680.9
- #6WebDev · Webdev-react1713.0
- #4Search Overall1241.6
- #1Document Overall1516.3
- #5Document Style Control Overall1489.7
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
- #3FrontierCode Main53.4%
- #5FrontierCode Extended63.6%
Ranks among Noumen catalog models on FrontierCode leaderboards. Only top-20 placements are listed.FrontierCode
- #7Epoch Capabilities Index163.9
- #4GPQA Diamond92.9%
Ranks among Noumen catalog models on Epoch AI leaderboards. Only top-20 placements are listed.Epoch AI
- #9ARC-AGI-197.5%
- #6ARC-AGI-290.4%
- #4ARC-AGI-3 (Default harness)30.2%
Ranks among Noumen catalog models on ARC Prize leaderboards. Only top-20 placements are listed.ARC Prize
- #1EQ-Bench 41360
- #3Creative Writing v32134
- #1Longform Writing86.3
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
- #12Game Development1339
- #13Website1309
- #6UI Component1345
- #9Data Visualization1330
- #7SVG1308
- #153D1331
- #1ASCII Art1358
- #3Agentic Game Dev1224
- #8Web Apps1266
- #5Full Stack1306
- #2Native Apps1256
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 116.0 tok/s
- Faster than 67% of 260 models
- Time to first token
- 4.4 s
- Quicker than 37% of 260 models
- Prompt cache hits
- 68.7%
- About $1.91 per 1M input tokens with caching
- Request success (24h)
- 99.9%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-opus-5",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="anthropic/claude-opus-5",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Anthropic
Related models
Other Anthropic models, starting with the same family.